Datatype

The notion of Data Type is central to Agents. Agents reason across multiple systems (structured and unstructured), and consistency in data structures is critical. That is where data types come in.

Why this matters: Consistent typing ensures that one tool’s output can be another tool’s input. Without types, chaining complex workflows would quickly break.

A Type has the following properties -

• name : such as “string” or “CustomerProfile” or “OrderDetails”

• description : that describes the object - e.g. this is the unique id that represents a customer in the system. If you have a limited set of values that the object can take then you can list them here or describe them. E.g. This represents a day of the week OR value can be one of [‘CANCELLED’, ‘COMPLETED’, ‘INPROGRESS]

• fields : optional fields that lists other fields for a Type that is an object

Primitives

• string — text values.

• integer — whole numbers.

• boolean — true/false.

• decimal — numbers with fractional values.

Objects

Objects group fields under a shared type. For example, a Customer object could look like this:

{
  "name": "Customer",
  "description": "Represents a customer record",
  "fields": {
    "id": { "type": "string", "description": "Unique customer ID" },
    "name": { "type": "string", "description": "Full name" },
    "active": { "type": "boolean", "description": "Is the customer active?" }
  }
}

Lists

Appending [] creates arrays, such as Order[] or string[].

{
  "name": "Customer",
  "description": "Represents a customer record",
  "fields": {
    "id": { "type": "string", "description": "Unique customer ID" },
    "name": { "type": "string", "description": "Full name" },
    "active": { "type": "boolean", "description": "Is the customer active?" }
  }
}

Objects group fields under a shared type. For example, a Customer object could look like this: